© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198356
    Prev
    Next
    INDEX
    Explanations

    events or states that existed

    np_acts-logits-general · gemini-2.5-flash-lite

    qualification after a statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рики
    0.46
    菩
    0.46
     crackers
    0.43
     troopers
    0.43
    據
    0.42
    瑪
    0.42
    ască
    0.41
    轉
    0.41
    테
    0.41
     spotting
    0.40
    POSITIVE LOGITS
    z
    0.61
    ed
    0.61
     ܡ
    0.55
    au
    0.54
    langan
    0.54
    r
    0.53
    j
    0.53
    t
    0.52
    en
    0.50
    um
    0.50
    Activations Density 0.000%

    No Known Activations